© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14103
    Prev
    Next
    INDEX
    Explanations

    thickness of your finger/pencil

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    कारात्मक
    1.14
     परा
    1.13
    सेस
    1.13
    𝑠
    1.13
    িবার
    1.09
    Includes
    1.09
    عه
    1.08
    ेंसिल
    1.07
     Applic
    1.06
     членом
    1.06
    POSITIVE LOGITS
    ர்ப்பு
    1.13
    HING
    1.12
    ের
    1.11
     togg
    1.10
     toggle
    1.09
     ascent
    1.09
    낯
    1.08
     experiment
    1.08
     tick
    1.08
     Mathematik
    1.07
    Activations Density 0.000%

    No Known Activations